From c7c57461ca526b5254cf4cc9e1b5575e5d6e507d Mon Sep 17 00:00:00 2001
From: tt-P607 <68868379+tt-P607@users.noreply.github.com>
Date: Fri, 26 Sep 2025 21:59:38 +0800
Subject: [PATCH] =?UTF-8?q?refactor(llm=5Fmodels):=20=E5=B0=86=E7=94=A8?=
 =?UTF-8?q?=E9=87=8F=E8=AE=B0=E5=BD=95=E5=87=BD=E6=95=B0=E6=94=B9=E4=B8=BA?=
 =?UTF-8?q?=E5=BC=82=E6=AD=A5=E4=BB=A5=E6=94=AF=E6=8C=81=E6=95=B0=E6=8D=AE?=
 =?UTF-8?q?=E5=BA=93=E5=86=99=E5=85=A5?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

将 `LLMUsageRecorder` 中的 `record_usage_to_database` 和 `LLMRequest` 中的 `_record_usage` 方法从同步转换为异步。

此项重构是为了支持异步数据库操作，避免在记录模型用量时阻塞事件循环，从而提升应用的整体性能和响应能力。
---
 src/llm_models/utils.py       | 4 ++--
 src/llm_models/utils_model.py | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/src/llm_models/utils.py b/src/llm_models/utils.py
index bf23f144a..f08ce2092 100644
--- a/src/llm_models/utils.py
+++ b/src/llm_models/utils.py
@@ -145,9 +145,9 @@ class LLMUsageRecorder:
     LLM使用情况记录器（SQLAlchemy版本）
     """
 
-    @staticmethod
     async def record_usage_to_database(
-            model_info: ModelInfo,
+        self,
+        model_info: ModelInfo,
         model_usage: UsageRecord,
         user_id: str,
         request_type: str,
diff --git a/src/llm_models/utils_model.py b/src/llm_models/utils_model.py
index 3ea94c1e1..cf2a7cb1c 100644
--- a/src/llm_models/utils_model.py
+++ b/src/llm_models/utils_model.py
@@ -891,7 +891,7 @@ class LLMRequest:
             max_tokens=self.model_for_task.max_tokens if max_tokens is None else max_tokens,
         )
 
-        self._record_usage(model_info, response.usage, time.time() - start_time, "/chat/completions")
+        await self._record_usage(model_info, response.usage, time.time() - start_time, "/chat/completions")
 
         if not response.content and not response.tool_calls:
             if raise_when_empty:
@@ -916,14 +916,14 @@ class LLMRequest:
             embedding_input=embedding_input
         )
         
-        self._record_usage(model_info, response.usage, time.time() - start_time, "/embeddings")
+        await self._record_usage(model_info, response.usage, time.time() - start_time, "/embeddings")
         
         if not response.embedding:
             raise RuntimeError("获取embedding失败")
         
         return response.embedding, model_info.name
 
-    def _record_usage(self, model_info: ModelInfo, usage: Optional[UsageRecord], time_cost: float, endpoint: str):
+    async def _record_usage(self, model_info: ModelInfo, usage: Optional[UsageRecord], time_cost: float, endpoint: str):
         """
         记录模型使用情况。